WS 2016/17

Representation Learning

 

Assignments 12: Deep Belief Networks & Deep Boltzmann Machines

Reading

In this reading assignment, we extend our focus on probablistic models with intractable posterior distributions.

Please read Deep Learning Book - Chapter 19: Approximate Inference for an overview on possible approaches. You can skip most of Section 19.4.1 as indicated in the text.

Then continue reading Deep Learning Book - Chapter 20: Deep Generative Models:

Section 20.5 is optional and will not be covered in the course.

Deadline for questions to be considered in class is January 21, 7am. I will also try to accommodate things that come in later but I cannot make guarantees. The earlier you bring up questions, the better.

Course Project

Like last week, we will spend about 50% of the time in class for discussing the reading assignments. This will leave less time for the course project. Therefore, if you would like to present and/or discuss progress on a specific aspect of the project, please prepare accordingly. Also, please send an email with the topic and the approximate amount of time required until January 23, 10am.